© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 86229
    Prev
    Next
    INDEX
    Explanations

    snare head

    np_acts-logits-general · gemini-2.5-flash-lite

    asking a question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    父亲
    0.42
     αγο
    0.41
     всіх
    0.39
    寳
    0.39
    会长
    0.38
    ৪
    0.38
    长
    0.38
    auteur
    0.38
    团体
    0.38
    Д
    0.38
    POSITIVE LOGITS
     eroded
    0.47
     deprecated
    0.47
     erode
    0.46
     Usually
    0.45
     decimated
    0.43
     Specify
    0.43
     They
    0.43
     carv
    0.42
     compressor
    0.42
     usually
    0.42
    Activations Density 0.000%

    No Known Activations